ODS Frushtuck Munich! Jeder ist wilkommen, aber offizielle sprache ist englisch.
ODS breakfast in Munchen! See you this Friday (27th) at 8:30 at
Schmalznudel - Cafe Frischhut
Prälat-Zistl-Straße 8, 80331 München
https://goo.gl/maps/LnX8QVpjDM6sDCNQ8
Evgenii +4916091541827
ODS breakfast in Munchen! See you this Friday (27th) at 8:30 at
Schmalznudel - Cafe Frischhut
Prälat-Zistl-Straße 8, 80331 München
https://goo.gl/maps/LnX8QVpjDM6sDCNQ8
Evgenii +4916091541827
ODS breakfast in Paris! See you this Saturday (28th) at 10:30 at Malongo Café, 50 Rue Saint-André des Arts.
🔥 Tensorflow 2.0 release
Faster
TPU support
TensorFlow datasets
Change log: https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab
#google #tensorflow #dl #tf
Faster
TPU support
TensorFlow datasets
Change log: https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab
#google #tensorflow #dl #tf
Medium
TensorFlow 2.0 is now available!
Earlier this year, we announced TensorFlow 2.0 in alpha at the TensorFlow Dev Summit. Today, we’re delighted to announce that the final…
🎓CS224W: Machine Learning with Graphs
Great course from #Stanford. You still on time to jump at studying from one of the best schools.
Students are introduced to machine learning techniques and data mining tools apt to reveal insights on the social, technological, and natural worlds, by means of studying their underlying network structure and interconnections.
Topics include: robustness and fragility of food webs and financial markets; algorithms for the World Wide Web; graph neural networks and representation learning; identification of functional modules in biological networks; disease outbreak detection.
Link: http://cs224w.stanford.edu
Videos link: http://snap.stanford.edu/class/cs224w-videos-2019/
#MOOC #entrylevel #wheretostart
Great course from #Stanford. You still on time to jump at studying from one of the best schools.
Students are introduced to machine learning techniques and data mining tools apt to reveal insights on the social, technological, and natural worlds, by means of studying their underlying network structure and interconnections.
Topics include: robustness and fragility of food webs and financial markets; algorithms for the World Wide Web; graph neural networks and representation learning; identification of functional modules in biological networks; disease outbreak detection.
Link: http://cs224w.stanford.edu
Videos link: http://snap.stanford.edu/class/cs224w-videos-2019/
#MOOC #entrylevel #wheretostart
GANs from Scratch 1: A deep introduction.
Great introduction and tutorial. With code in PyTorch and TensorFlow
Link: https://medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f
#tensorflow #pytorch #GAN #tutorial #entrylevel #novice #wheretostart
Great introduction and tutorial. With code in PyTorch and TensorFlow
Link: https://medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f
#tensorflow #pytorch #GAN #tutorial #entrylevel #novice #wheretostart
Classification and Loss Evaluation - Softmax and Cross Entropy Loss
Nice notes on softmax cross entropy loss and how to implement it in numpy.
Link: https://deepnotes.io/softmax-crossentropy
#nn #entrylevel #wheretostart
Nice notes on softmax cross entropy loss and how to implement it in numpy.
Link: https://deepnotes.io/softmax-crossentropy
#nn #entrylevel #wheretostart
Parasdahal
Softmax and Cross Entropy Loss
Understanding the intuition and maths behind softmax and the cross entropy loss - the ubiquitous combination in classification algorithms.
Big scandal on popular YouTuber ML course
Siraj Raval, who raised his audience on devliering various YouTube videos, explaning #ML and #DL concepts as long with interviews with leading persons, launched his own course, but failed to provide much value.
His course was built on open and free tutorials, created by passionate enthusiasts, but he failed to attribute them properly and charged money for ununique content without any proper support for students.
He also oversold his course and tried to hide that from students, claiming to provide personal feedbacks, but failing to do so due to being too greedy.
Most of the best online courses and study programms are available online and for free, including those, we gathered here on our channel and attributed with hastags #wheretostart #entrylevel #MOOC #tutorial. Feel free to click these hashtags and browse for best available resources to start learning data science.
Link: https://www.theregister.co.uk/AMP/2019/09/27/youtube_ai_star
Siraj Raval, who raised his audience on devliering various YouTube videos, explaning #ML and #DL concepts as long with interviews with leading persons, launched his own course, but failed to provide much value.
His course was built on open and free tutorials, created by passionate enthusiasts, but he failed to attribute them properly and charged money for ununique content without any proper support for students.
He also oversold his course and tried to hide that from students, claiming to provide personal feedbacks, but failing to do so due to being too greedy.
Most of the best online courses and study programms are available online and for free, including those, we gathered here on our channel and attributed with hastags #wheretostart #entrylevel #MOOC #tutorial. Feel free to click these hashtags and browse for best available resources to start learning data science.
Link: https://www.theregister.co.uk/AMP/2019/09/27/youtube_ai_star
The Register
YouTuber charged loads of fans $199 for shoddy machine-learning course that copy-pasted other people's GitHub code
And there wasn't a refund policy until folk complained
GPT-2 hadn’t (yet) fooled jury at The Economist’s Open Future Essay Contest
Though one of the judges suggested that «It is strongly worded and backs up claims with evidence, but the idea is not incredibly original.»
Link: https://www.economist.com/open-future/2019/10/01/how-to-respond-to-climate-change-if-you-are-an-algorithm
#NLP #GPT2 #NLU
Though one of the judges suggested that «It is strongly worded and backs up claims with evidence, but the idea is not incredibly original.»
Link: https://www.economist.com/open-future/2019/10/01/how-to-respond-to-climate-change-if-you-are-an-algorithm
#NLP #GPT2 #NLU
The Economist
How to respond to climate change, if you are an algorithm
We ran our youth essay question through an artificial-intelligence system to produce an essay
27,600 V100 GPUs, 0.5 PB data, and a neural net with 220,000,000 weights
If you wonder, it all was used to address scientific inverse problem in materials imaging.
ArXiV: https://arxiv.org/pdf/1909.11150.pdf
#ItIsNotAboutSize #nn #dl
If you wonder, it all was used to address scientific inverse problem in materials imaging.
ArXiV: https://arxiv.org/pdf/1909.11150.pdf
#ItIsNotAboutSize #nn #dl
📹Artificial caricature
Agents learn to draw simplified (artistic?) portraits via trial and error.
Project website: https://learning-to-paint.github.io
ArXiV: https://arxiv.org/abs/1910.01007
#GAN #CelebA #DL
Agents learn to draw simplified (artistic?) portraits via trial and error.
Project website: https://learning-to-paint.github.io
ArXiV: https://arxiv.org/abs/1910.01007
#GAN #CelebA #DL
Forwarded from Находки в опенсорсе
#strange
An awesome list of dev-related movies: https://github.com/aryaminus/dev-movies
In case you don't have enough of development at work!
An awesome list of dev-related movies: https://github.com/aryaminus/dev-movies
In case you don't have enough of development at work!
GitHub
GitHub - aryaminus/dev-movies: Movies and Series I've loved over the years, for the people with software development background…
Movies and Series I've loved over the years, for the people with software development background, IT Engineers or general people who love movies - GitHub - aryaminus/dev-movies: Movies and ...
Video on how Facebook continues to develop its #Portal device
How #Facebook used Mask R-CNN, #PyTorch, and custom hardware integrations like foveated processing to improve Portal’s Smart Camera system.
Link: https://ai.facebook.com/blog/smart-camera-portal-advances/
#CV #DL #Segmentation
How #Facebook used Mask R-CNN, #PyTorch, and custom hardware integrations like foveated processing to improve Portal’s Smart Camera system.
Link: https://ai.facebook.com/blog/smart-camera-portal-advances/
#CV #DL #Segmentation
Meta
How we’ve advanced Smart Camera for new Portal video-calling devices
We’ve used Detectron2, Mask R-CNN, and custom hardware integrations like foveated processing in order to make additional speed and precision improvements in the computer vision models that power Smart Camera.
8 Deep Learning / Computer Vision Bugs And How I Could Have Avoided Them
Nice article about common pitfalls in #CV and #DL
Link: https://medium.com/@arseny_info/8-deep-learning-computer-vision-bugs-and-how-i-could-have-avoided-them-d40b0e4b1da
Nice article about common pitfalls in #CV and #DL
Link: https://medium.com/@arseny_info/8-deep-learning-computer-vision-bugs-and-how-i-could-have-avoided-them-d40b0e4b1da
Medium
8 Deep Learning / Computer Vision Bugs And How I Could Have Avoided Them
People are not perfect, we often make bugs in our software. Sometimes these bugs are easy to find: your code just doesn’t work at all…
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
High-quality #speechrecognition systems require large amounts of data—yet many languages have little data available. Check out new research into an end-to-end system trained as a single model allowing for real-time multilingual speech recognition.
Link: https://ai.googleblog.com/2019/09/large-scale-multilingual-speech.html
#speech #audio #DL #Google
High-quality #speechrecognition systems require large amounts of data—yet many languages have little data available. Check out new research into an end-to-end system trained as a single model allowing for real-time multilingual speech recognition.
Link: https://ai.googleblog.com/2019/09/large-scale-multilingual-speech.html
#speech #audio #DL #Google
research.google
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
Posted by Arindrima Datta and Anjuli Kannan, Software Engineers, Google Research Google's mission is not just to organize the world's information b...
Library for Scikit-learn parallelization
Operations like grid search, random forest, and others that use the njobs parameter in Scikit-Learn can automatically hand-off parallelism to a Dask cluster.
Link: https://ml.dask.org/joblib.html
#ML #scikitlearn
Operations like grid search, random forest, and others that use the njobs parameter in Scikit-Learn can automatically hand-off parallelism to a Dask cluster.
Link: https://ml.dask.org/joblib.html
#ML #scikitlearn